AI TrackerFrontier desk · AEST
Back to news
normalaitech

SciExam for ENSO: Can AI Agents Build Climate Models?

arXiv cs.AI · 8 Oct 2026, 03:52 AEST

AI agents are being tested for their ability to build climate models through a new benchmark called SciExam for ENSO. The results indicate that some agents can produce models that outperform existing published models in reconstructing and forecasting climate variability.

Key facts

Read aloud

A I agents are being tested for their ability to build climate models through a new benchmark called SciExam for ENSO. The results indicate that some agents can produce models that outperform existing published models in reconstructing and forecasting climate variability. The A I Science Exam for El Nino-Southern Oscillation SciExam for ENSO is a benchmark in which agents build low-order stochastic models of ENSO, the dominant mode of interannual climate variability, from real observations. Across twelve agent systems, six produce models that score higher than the published model, mainly through better reconstruction and forecasting. Controlled runs of the top system under varied information suggest that its scores do not come from recalling the dated observational record and that the information it receives shapes how it builds its model.

Sources in this cluster